Project Halo: Towards a Digital Aristotle
by Friedland, Noah and Allen, Paul, and Mathews, Gavin and Whitbrock, Michael, and Baxter, David and Curtis, Jon and Shepard, Blake and Miraglia, Pierluigi and Angele, Jurgen and Staab, Stephen, and Moench, Eddie and Opperman, Henrik and Wenke, Dirk and Israel, David and Chaudhri, Vinay and Porter, Bruce and Barker, Ken and Fan, James and Chaw, Shaw Yi and Yeh, Peter, Tecuci, Dan and Clark, Peter
AI Magazine, 2004.
Project Halo is a multi-staged effort, sponsored by Vulcan Inc, aimed at creating the Digital Aristotle, an application that will encompass much of the worlds scientific knowledge and be capable of applying sophisticated problem solving to answer novel questions. Vulcan envisions two primary roles for the Digital Aristotle: as a tutor to instruct students in the sciences, and as an interdisciplinary research assistant to help scientists in their work.
As a first step towards this goal, we have just completed a six-month Pilot phase, designed to assess the state of the art in applied Knowledge Representation and Reasoning (KR&R). Vulcan selected three teams, each of which was to formally represent 70 pages from the Advanced Placement (AP) chemistry syllabus and deliver knowledge based systems capable of answering questions on that syllabus. The evaluation quantified each systems coverage of the syllabus in terms of its ability to answer novel, previously unseen questions and to provide human-readable answer justifications. These justifications will play a critical role in building user trust in the question-answering capabilities of the Digital Aristotle.
Prior to the final evaluation, a failure taxonomy was collaboratively developed in an attempt to standardize failure analysis and to facilitate cross-platform comparisons. Despite differences in approach, all three systems did very well on the challenge, achieving performance comparable to the human median. The analysis also provided key insights into how the approaches might be scaled, while at the same time suggesting how the cost of producing such systems might be reduced. This outcome leaves us highly optimistic that the technical challenges facing this effort in the years to come can be identified and overcome.
This paper presents the motivation and long-term goals of Project Halo, describes in detail the 6-month first phase of the project the Halo Pilot its KR&R challenge, empirical evaluation, results and failure analysis. The pilots outcome is used to define challenges for the next phase of the project and beyond.
The goal of the project is to demonstrate the current state-of-the-art in knowledge representation by attempting to answer the questions in an advance placement test in chemistry.
|Barker, Ken||Research Associate, Univ. of Texas-Austin|
|Chaudhri, Vinay K||Program Director|
|Clark, Peter E.||Allen Institute of Artificial Intelligence|
|Israel, David J||Program Director|
|Porter, Bruce||Professor, University of Texas at Austin|